Denoising Diffusion-Based Image Generation Model Using Principal Component Analysis

In recent years, advancements in GPU technology and increased data collection have significantly enhanced the performance of artificial intelligence and image generation models. However, in specific areas such as medical imaging or facial images, constraints in data collection and class imbalance is...

Full description

Saved in:
Bibliographic Details
Main Authors: Myung Keun Song, Asim Niaz, Muhammad Umraiz, Ehtesham Iqbal, Shafiullah Soomro, Kwang Nam Choi
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10755095/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850236667217051648
author Myung Keun Song
Asim Niaz
Muhammad Umraiz
Ehtesham Iqbal
Shafiullah Soomro
Kwang Nam Choi
author_facet Myung Keun Song
Asim Niaz
Muhammad Umraiz
Ehtesham Iqbal
Shafiullah Soomro
Kwang Nam Choi
author_sort Myung Keun Song
collection DOAJ
description In recent years, advancements in GPU technology and increased data collection have significantly enhanced the performance of artificial intelligence and image generation models. However, in specific areas such as medical imaging or facial images, constraints in data collection and class imbalance issues have posed challenges to improving image quality. This study proposes the integration of Principal Component Analysis (PCA) into image generation models to address these challenges. Specifically, to overcome the limitations of conventional image generation models like GANs and VAEs, we utilize the Denoise Diffusion Probabilistic Model (DDPM) as the backbone, integrating it with PCA techniques. Using the CIFAR10 and FFHQ datasets, we evaluated the image quality of the proposed PCA-DDPM, the traditional DDPM, and DCGAN. As a result, the PCA-DDPM demonstrated superior image quality and efficiency. Notably, it maintained high performance even when trained with a limited amount of data. The findings of this research contribute significantly to the advancement of image generation technology and are expected to be applied in various domains.
format Article
id doaj-art-54c6705fc36c4bf9a7ee09c605fcc0b6
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-54c6705fc36c4bf9a7ee09c605fcc0b62025-08-20T02:01:54ZengIEEEIEEE Access2169-35362024-01-011217048717049810.1109/ACCESS.2024.350021210755095Denoising Diffusion-Based Image Generation Model Using Principal Component AnalysisMyung Keun Song0https://orcid.org/0009-0003-8235-2228Asim Niaz1https://orcid.org/0000-0003-3905-9774Muhammad Umraiz2Ehtesham Iqbal3Shafiullah Soomro4https://orcid.org/0000-0002-4318-5055Kwang Nam Choi5https://orcid.org/0000-0002-7420-9216Department of Computer Science and Engineering, Chung-Ang University, Seoul, Republic of KoreaDepartment of Computer Science and Engineering, Chung-Ang University, Seoul, Republic of KoreaDepartment of Computer Science and Engineering, Chung-Ang University, Seoul, Republic of KoreaAdvanced Research and Innovation Center (ARIC), Khalifa University of Science and Technology, Abu Dhabi, United Arab EmiratesDepartment of Computer Science and Media Technology, Linnaeus University, Växjö, SwedenDepartment of Computer Science and Engineering, Chung-Ang University, Seoul, Republic of KoreaIn recent years, advancements in GPU technology and increased data collection have significantly enhanced the performance of artificial intelligence and image generation models. However, in specific areas such as medical imaging or facial images, constraints in data collection and class imbalance issues have posed challenges to improving image quality. This study proposes the integration of Principal Component Analysis (PCA) into image generation models to address these challenges. Specifically, to overcome the limitations of conventional image generation models like GANs and VAEs, we utilize the Denoise Diffusion Probabilistic Model (DDPM) as the backbone, integrating it with PCA techniques. Using the CIFAR10 and FFHQ datasets, we evaluated the image quality of the proposed PCA-DDPM, the traditional DDPM, and DCGAN. As a result, the PCA-DDPM demonstrated superior image quality and efficiency. Notably, it maintained high performance even when trained with a limited amount of data. The findings of this research contribute significantly to the advancement of image generation technology and are expected to be applied in various domains.https://ieeexplore.ieee.org/document/10755095/Artificial intelligencedeep learningdenoising diffusionimage generationprincipal component analysis
spellingShingle Myung Keun Song
Asim Niaz
Muhammad Umraiz
Ehtesham Iqbal
Shafiullah Soomro
Kwang Nam Choi
Denoising Diffusion-Based Image Generation Model Using Principal Component Analysis
IEEE Access
Artificial intelligence
deep learning
denoising diffusion
image generation
principal component analysis
title Denoising Diffusion-Based Image Generation Model Using Principal Component Analysis
title_full Denoising Diffusion-Based Image Generation Model Using Principal Component Analysis
title_fullStr Denoising Diffusion-Based Image Generation Model Using Principal Component Analysis
title_full_unstemmed Denoising Diffusion-Based Image Generation Model Using Principal Component Analysis
title_short Denoising Diffusion-Based Image Generation Model Using Principal Component Analysis
title_sort denoising diffusion based image generation model using principal component analysis
topic Artificial intelligence
deep learning
denoising diffusion
image generation
principal component analysis
url https://ieeexplore.ieee.org/document/10755095/
work_keys_str_mv AT myungkeunsong denoisingdiffusionbasedimagegenerationmodelusingprincipalcomponentanalysis
AT asimniaz denoisingdiffusionbasedimagegenerationmodelusingprincipalcomponentanalysis
AT muhammadumraiz denoisingdiffusionbasedimagegenerationmodelusingprincipalcomponentanalysis
AT ehteshamiqbal denoisingdiffusionbasedimagegenerationmodelusingprincipalcomponentanalysis
AT shafiullahsoomro denoisingdiffusionbasedimagegenerationmodelusingprincipalcomponentanalysis
AT kwangnamchoi denoisingdiffusionbasedimagegenerationmodelusingprincipalcomponentanalysis